mcp-weather

mcp-weather

Provides morning/lunch/evening weather and fine dust (PM10/PM2.5) data for multiple locations using Korean weather and air quality APIs, outputting structured text suitable for daily reports.

Category
Visit Server

README

mcp-weather

여러 위치의 오늘 아침/점심/저녁 날씨(기상청 단기예보)와 미세먼지(에어코리아)를 반환하는 MCP 서버.

출력은 구조화 텍스트(데일리 리포트용). LLM이 사실로 소비하도록 설계됨.

도구

get_weather

입력: { locations: [{ name, lat, lon }] } (여러 곳 한 번에)

필드 타입 설명
name string 위치 이름
lat number 위도 (WGS84)
lon number 경도 (WGS84)

출력(위치별): 아침(06-09)·점심(12-15)·저녁(18-21) 기온·하늘상태·강수확률 + 미세먼지 PM10/PM2.5 수치·등급(좋음/보통/나쁨/매우나쁨)·측정소명.

예시:

📍 안양 (37.394, 126.957)
아침(06-09) 18~23°C · 맑음 · 강수 30%
점심(12-15) 22~30°C · 비 · 강수 60%
저녁(18-21) 21~27°C · 비 · 강수 60%
미세먼지 PM10 11 (좋음) · PM2.5 6 (좋음)  [측정소: 부림동]

환경변수 (키)

data.go.kr 일반 인증키 1개로 KMA + AirKorea 모두 사용. .env(커밋 금지, .env.example 참고):

KMA_SERVICE_KEY=YOUR_DATA_GO_KR_KEY
AIRKOREA_SERVICE_KEY=YOUR_DATA_GO_KR_KEY

키는 절대 커밋하지 않는다(.env는 .gitignore). 발급 직후 ~1시간 동기화 지연이 있을 수 있다.

설치

git clone https://github.com/molpass/mcp-weather.git
cd mcp-weather
npm install && npm run build

예제(세 좌표 라이브, 키 필요):

KMA_SERVICE_KEY=... AIRKOREA_SERVICE_KEY=... npm run example

Hermes / MCP 등록

{
  "mcpServers": {
    "weather": {
      "command": "node",
      "args": ["/abs/path/mcp-weather/dist/index.js"],
      "env": { "KMA_SERVICE_KEY": "...", "AIRKOREA_SERVICE_KEY": "..." }
    }
  }
}

/abs/path 는 클론한 실제 절대경로로 바꾼다. Windows 예: "C:/Users/<you>/mcp-weather/dist/index.js".

스택

  • Node 20+ / TypeScript · @modelcontextprotocol/sdk (stdio) · proj4 (WGS84→TM 변환)
  • 소스: 기상청 단기예보 getVilageFcst · 에어코리아 getNearbyMsrstnList + getMsrstnAcctoRltmMesureDnsty
  • 좌표: lat/lon → KMA LCC 격자(nx/ny) · lat/lon → TM(EPSG:5181, 근접 측정소용)

스킬

페어링 스킬: skill/weather.skill.md — 의도를 get_weather 파라미터로 매핑한다.

About / 제작

Hermes Agent용 MCP — molpass의 바이브 코딩(vibe coding) 프로젝트.

  • 아이디어·방향: molpass (이정훈) · https://zeolinex.com
  • 기획: Claude (Chat)
  • 개발: Claude Code

자가 호스팅 Hermes Agent에 도구로 붙여 쓰는 MCP 서버입니다.

같은 모음:

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured